|
Abstract
|
A new generalization of the Weibull-G family is proposed with two extra shape param-
eters. The mathematical properties are derived in great detail. Using the Weibull and
normal distributions as baseline distributions, two models are introduced. The first
model is a location-scale regression model based on a new extension of the Weibull
distribution. The second model is a new two-step financial risk model to forecast the
daily value at risk. The flexibility and applicability of the proposed models are inves-
tigated by means of five real data sets on the lifetime and financial returns. Empirical
findings of the study show that proposed models work well and produce better results
than other well-known models for financial risk modeling and censored lifetime data
analysis.
|